Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12336
    Prev
    Next
    INDEX
    Explanations

    the word "marsh" with strong emphasis

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "marshmallow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deaf
    -0.83
    wcs
    -0.77
     livest
    -0.73
    hedral
    -0.70
     thumbs
    -0.68
     tense
    -0.67
    versions
    -0.67
     vest
    -0.66
    ggle
    -0.66
     inert
    -0.64
    POSITIVE LOGITS
    mallow
    1.83
    alling
    1.19
    alled
    1.05
    aling
    1.01
    adow
    0.99
    alls
    0.94
    als
    0.93
    lands
    0.91
    ateur
    0.91
     Marshal
    0.90
    Activations Density 0.016%

    No Known Activations